In this article, a new framework is proposed and implemented for automatic generation of image filters in reconfigurable hardware (FPGA), called H-EHW (Hybrid-Evolvable Hardware). This consists basically of two modules. The first (training module) is responsible for the automatic generation of solutions (filters). The second (fusion module) converts such solutions into hardware, thus creating a virtual and reconfigurable architecture for fast image processing. Monochromatic pairs of images are used for the system training and testing. Extensive tests show that there are several benefits of the proposed system when compared to other similar systems described in the literature, such as: reduced phenotype length (generated circuit), reduced reconfiguration time, greater hardware reconfiguration flexibility and no more need for the manipulation of the bitstream of the FPGA for circuit evolution (a problem often encountered in practice by designers).
AdeliHHungSL. Machine Learning – Neural Networks, Genetic Algorithms, and Fuzzy Sets. John Wiley and Sons, New York, 1995.
2.
CancareFBhandariSBartoliniDBCarminatiMSantambrogioMD. A bird’s eye view of FPGA-based Evolvable Hardware. In NASA/ESA Conference on Adaptive Hardware and Systems, 2011.
3.
CaponioACascellaGLNeriFSalvatoreNSummerM. A fast adaptive memetic algorithm for online and offline control design of PMSM drives. IEEE Transactions on Systems, Man, and Cybernetics – Part B: Cybenetics2007; 37(1): 28-41.
4.
GallagherJCVigrahamS. A modified compact genetic algorithm for the intrinsic evolution of continuous time recurrent neural networks. In Proc 2002 Genetic Evolutionary Computation Conference2002; 163-170.
5.
GletteKTorresenJYasunagaM. On-chip evolution using a soft processor core applied to image recognition. In Adaptive Hardware and Systems, AHS First NASA/ESA Conference, 2006.
6.
GletteKTorresenJHovinM. Intermediate level FPGA reconfiguration for an online EHW pattern recognition system. In NASA/ESA Conference on Adaptive Hardware and Systems. San Francisco, CA2009; 19-26.
7.
GonzalezRCWoodsRE. Digital Image Processing. Prentice Hall, 2008.
8.
GreenstedAJTyrrelAM. Extrinsic Evolvable Hardware on the RTSA architecture. In Proceedings of International Conference on Evolvable Systems, 2007.
9.
HungSLAdeliH. An adaptive conjugate gradient learning algorithm for effective training of multilayer neural networks. Applied Mathematics and Computation1994; 62(1): 81-102.
10.
HungSLAdeliH. A parallel genetic/neural network learning algorithm for MIMD shared memory machines. IEEE Transactions on Neural Networks1994; 5(6): 900-909.
KalganovaT. Bidirectional incremental evolution in extrinsic evolvable hardware. In Proceedings of the Second NASA/DoD Workshop on Evolvable Hardware, Palo Alto, CA2000; 65-74.
13.
KozaJR. Genetic programming: On the programming of computers by natural selection. Massachusetts: MIT Press Cambridge, 1992.
14.
LambertCKalganovaTStomeoE. FPGA-based Systems for Evolvable Hardware. International Journal of Electrical, Computer and Systems Engineering2009; 3: 62-68.
15.
MillerJFThomsonPFogartyTC. Designing electronic circuits using genetic algorithms and evolution strategies in engineering and computer science. In Second Eurogen Course, Trieste, 1997.
16.
MoraJGallegoÁOteroALopezBTorreEDLRiesgoT. Noise-agnostic self-adaptive image processing application based on Evolvable Hardware. In Design and Architectures for Signal and Image Processing Conference (DASIP), 2013.
17.
OreifejRSAl-HaddadRNTanHDeMaraRF. Layered approach to intrinsic evolvable hardware using direct bitstream manipulation of Virtex II Pro devices. In International Conference on Field Programmable Logic and Applications, Amsterdam2007; 299-304.
18.
ParisPCDPedrinoECNicolettiMC. Automatic learning of image filters using Cartesian genetic programming. Integrated Computer-Aided Engineering2015; 22: 135-151.
19.
PedrinoEC. Reconfigurable pipelined architecture through instructions generated by genetic programming for morphological image processing using FPGAs. Doctorate Thesis, Sao Paulo University at Sao Carlos, School of Engineering, 2008.
20.
PedrinoECSaitoJHRodaVOKatoERRTroncoMLTsunakiRHMorandinO. Automatic construction of image operators using a genetic programming approach. In Proc of the 11th International Conference on Intelligent Systems Design and Applications, Cordoba, Spain2011; 636-641.
21.
PorterRBBergmannNW. Evolving FPGA based cellular automata. In Selected Papers from the Second Asia-Pacific Conference on Simulated Evolution and Learning on Simulated Evolution and Learning1998; 114-121.
22.
SalvadorROteroAMoraJTorreEDLRiesgoTSekaninaL. Self-reconfigurable Evolvable Hardware system for adaptive image processing. IEEE Transactions on Computers2013; 62(8): 1481-1493.
23.
SilvaSAlmeidaJ. GPLAB – a genetic programming toolbox for MATLAB. In Proceedings of the Nordic MATLAB Conference2003; 273-278.
24.
SekaninaLFriedlS. An evolvable combinational unit for FPGAs. Computing and Informatics2004; 23: 461-486.
25.
SekaninaL. Evolutionary functional recovery in virtual reconfigurable circuits. ACM Journal on Emerging Technologies in Computing Systems2007; 3: 1-22.
26.
TirronemVNeriFKärkkäinenTMajavaKRossiT. An enhanced memetic differential evolution in filter design for defect detection in paper production. Evolutionary Computation2008; 16(4): 529-555.
27.
TorresenJ. Increased complexity evolution applied to evolvable hardware. In Smart Engineering System Design: Neural Networks, Fuzzy Logic, Evolutionary Programming, Data Mining, and Complex Systems, Proc of ANNIE’99’, 1999.
28.
ThompsonA. On the automatic design of robust electronics through artificial evolution. In Proceedings of the 2nd International Conference on Evolvable Systems: From Biology to Hardware, Lecture Notes in Computer Science, Springer-Verlag1998; 13-24.
29.
ThompsonA. An evolved circuit, intrinsic in silicon, entwined with physics. In Proceedings of the 1st International Conference on Evolvable Systems: From Biology to Hardware, Lecture Notes in Computer Science, Springer-Verlag1997; 390-405.
30.
VasicekZSekaninaL. Evaluation of a new platform for image filter evolution. In Second NASA/ESA Conference on Adaptive Hardware and Systems2007; 577-586.
31.
VasicekZSekaninaLBidloM. A method for design of impulse bursts noise filters optimized for FPGA implementations. In Design, Automation & Test in Europe Conference & Exhibition2010; 1731-1736.
32.
WangJChenQSLeeCH. Design and implementation of a virtual reconfigurable architecture for different applications of intrinsic evolvable hardware. IET Computers & Digital Techniques2007; 2: 386-400.
33.
YaoRSunYHeKYangY. Online evolution of image filters based on dynamic partial reconfiguration of FPGA. In 11th International Conference on Natural Computation (ICNC)2015; 999-1005.
